http://git-wip-us.apache.org/repos/asf/bigtop/blob/e209fdbb/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/bucketmapjoin5/out ---------------------------------------------------------------------- diff --git a/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/bucketmapjoin5/out b/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/bucketmapjoin5/out deleted file mode 100644 index c090210..0000000 --- a/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/bucketmapjoin5/out +++ /dev/null @@ -1,1015 +0,0 @@ -CREATE TABLE srcbucket_mapjoin(key int, value string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE - -load data local inpath 'seed_data_files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin -Copying file: file:/root/bigtop/bigtop-tests/test-execution/smokes/hive/target/seed_data_files/srcbucket20.txt - -load data local inpath 'seed_data_files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin -Copying file: file:/root/bigtop/bigtop-tests/test-execution/smokes/hive/target/seed_data_files/srcbucket21.txt - - -CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE - -load data local inpath 'seed_data_files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') -Copying file: file:/root/bigtop/bigtop-tests/test-execution/smokes/hive/target/seed_data_files/srcbucket20.txt - -load data local inpath 'seed_data_files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') -Copying file: file:/root/bigtop/bigtop-tests/test-execution/smokes/hive/target/seed_data_files/srcbucket21.txt - -load data local inpath 'seed_data_files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') -Copying file: file:/root/bigtop/bigtop-tests/test-execution/smokes/hive/target/seed_data_files/srcbucket22.txt - -load data local inpath 'seed_data_files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') -Copying file: file:/root/bigtop/bigtop-tests/test-execution/smokes/hive/target/seed_data_files/srcbucket23.txt - -load data local inpath 'seed_data_files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-09') -Copying file: file:/root/bigtop/bigtop-tests/test-execution/smokes/hive/target/seed_data_files/srcbucket20.txt - -load data local inpath 'seed_data_files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-09') -Copying file: file:/root/bigtop/bigtop-tests/test-execution/smokes/hive/target/seed_data_files/srcbucket21.txt - -load data local inpath 'seed_data_files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-09') -Copying file: file:/root/bigtop/bigtop-tests/test-execution/smokes/hive/target/seed_data_files/srcbucket22.txt - -load data local inpath 'seed_data_files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-09') -Copying file: file:/root/bigtop/bigtop-tests/test-execution/smokes/hive/target/seed_data_files/srcbucket23.txt - - -CREATE TABLE srcbucket_mapjoin_part_2 (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE - -load data local inpath 'seed_data_files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08') -Copying file: file:/root/bigtop/bigtop-tests/test-execution/smokes/hive/target/seed_data_files/srcbucket22.txt - -load data local inpath 'seed_data_files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08') -Copying file: file:/root/bigtop/bigtop-tests/test-execution/smokes/hive/target/seed_data_files/srcbucket23.txt - -load data local inpath 'seed_data_files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-09') -Copying file: file:/root/bigtop/bigtop-tests/test-execution/smokes/hive/target/seed_data_files/srcbucket22.txt - -load data local inpath 'seed_data_files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-09') -Copying file: file:/root/bigtop/bigtop-tests/test-execution/smokes/hive/target/seed_data_files/srcbucket23.txt - - -create table bucketmapjoin_hash_result_1 (key bigint , value1 bigint, value2 bigint) - -create table bucketmapjoin_hash_result_2 (key bigint , value1 bigint, value2 bigint) -set hive.optimize.bucketmapjoin = true - -create table bucketmapjoin_tmp_result (key string , value1 string, value2 string) - - -explain extended -insert overwrite table bucketmapjoin_tmp_result -select /*+mapjoin(a)*/ a.key, a.value, b.value -from srcbucket_mapjoin a join srcbucket_mapjoin_part b -on a.key=b.key -ABSTRACT SYNTAX TREE: - (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin) a) (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin_part) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME bucketmapjoin_tmp_result))) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST a))) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value))))) - -STAGE DEPENDENCIES: - Stage-9 is a root stage - Stage-1 depends on stages: Stage-9 - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 - Stage-5 - Stage-6 depends on stages: Stage-5 - -STAGE PLANS: - Stage: Stage-9 - Map Reduce Local Work - Alias -> Map Local Tables: - a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - a - TableScan - alias: a - GatherStats: false - HashTable Sink Operator - condition expressions: - 0 {key} {value} - 1 {value} - handleSkewJoin: false - keys: - 0 [Column[key]] - 1 [Column[key]] - Position of Big Table: 1 - Bucket Mapjoin Context: - Alias Bucket Base File Name Mapping: - a {ds=2008-04-08/srcbucket20.txt=[srcbucket20.txt], ds=2008-04-08/srcbucket21.txt=[srcbucket21.txt], ds=2008-04-08/srcbucket22.txt=[srcbucket20.txt], ds=2008-04-08/srcbucket23.txt=[srcbucket21.txt], ds=2008-04-09/srcbucket20.txt=[srcbucket20.txt], ds=2008-04-09/srcbucket21.txt=[srcbucket21.txt], ds=2008-04-09/srcbucket22.txt=[srcbucket20.txt], ds=2008-04-09/srcbucket23.txt=[srcbucket21.txt]} - Alias Bucket File Name Mapping: - a {hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket20.txt=[hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket20.txt], hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket21.txt=[hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket21.txt], hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket22.txt=[hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket20.txt], hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket23.txt=[hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket21.txt], hdfs://mgrover-bigtop-centos-1 .ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09/srcbucket20.txt=[hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket20.txt], hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09/srcbucket21.txt=[hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket21.txt], hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09/srcbucket22.txt=[hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket20.txt], hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09/srcbucket23.txt=[hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket21.txt]} - Alias Bucket Output File Name Mapping: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket20.txt 0 - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket21.txt 1 - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket22.txt 2 - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket23.txt 3 - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09/srcbucket20.txt 0 - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09/srcbucket21.txt 1 - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09/srcbucket22.txt 2 - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09/srcbucket23.txt 3 - - Stage: Stage-1 - Map Reduce - Alias -> Map Operator Tree: - b - TableScan - alias: b - GatherStats: false - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} {value} - 1 {value} - handleSkewJoin: false - keys: - 0 [Column[key]] - 1 [Column[key]] - outputColumnNames: _col0, _col1, _col5 - Position of Big Table: 1 - Select Operator - expressions: - expr: _col0 - type: int - expr: _col1 - type: string - expr: _col5 - type: string - outputColumnNames: _col0, _col1, _col5 - Select Operator - expressions: - expr: _col0 - type: int - expr: _col1 - type: string - expr: _col5 - type: string - outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - GlobalTableId: 1 - directory: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10002 - NumFilesPerFileSink: 1 - Stats Publishing Key Prefix: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10000/ - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value1,value2 - columns.types string:string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result - name default.bucketmapjoin_tmp_result - serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - transient_lastDdlTime 1366743639 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucketmapjoin_tmp_result - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - Local Work: - Map Reduce Local Work - Needs Tagging: false - Path -> Alias: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08 [b] - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09 [b] - Path -> Partition: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08 - Partition - base file name: ds=2008-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - properties: - bucket_count 4 - bucket_field_name key - columns key,value - columns.types int:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08 - name default.srcbucket_mapjoin_part - numFiles 4 - numPartitions 2 - numRows 0 - partition_columns ds - rawDataSize 0 - serialization.ddl struct srcbucket_mapjoin_part { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 - transient_lastDdlTime 1366743633 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count 4 - bucket_field_name key - columns key,value - columns.types int:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part - name default.srcbucket_mapjoin_part - numFiles 8 - numPartitions 2 - numRows 0 - partition_columns ds - rawDataSize 0 - serialization.ddl struct srcbucket_mapjoin_part { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 11624 - transient_lastDdlTime 1366743636 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcbucket_mapjoin_part - name: default.srcbucket_mapjoin_part - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09 - Partition - base file name: ds=2008-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - properties: - bucket_count 4 - bucket_field_name key - columns key,value - columns.types int:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09 - name default.srcbucket_mapjoin_part - numFiles 4 - numPartitions 2 - numRows 0 - partition_columns ds - rawDataSize 0 - serialization.ddl struct srcbucket_mapjoin_part { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 - transient_lastDdlTime 1366743636 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count 4 - bucket_field_name key - columns key,value - columns.types int:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part - name default.srcbucket_mapjoin_part - numFiles 8 - numPartitions 2 - numRows 0 - partition_columns ds - rawDataSize 0 - serialization.ddl struct srcbucket_mapjoin_part { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 11624 - transient_lastDdlTime 1366743636 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcbucket_mapjoin_part - name: default.srcbucket_mapjoin_part - Truncated Path -> Alias: - /srcbucket_mapjoin_part/ds=2008-04-08 [b] - /srcbucket_mapjoin_part/ds=2008-04-09 [b] - - Stage: Stage-7 - Conditional Operator - - Stage: Stage-4 - Move Operator - files: - hdfs directory: true - source: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10002 - destination: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10000 - - Stage: Stage-0 - Move Operator - tables: - replace: true - source: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10000 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value1,value2 - columns.types string:string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result - name default.bucketmapjoin_tmp_result - serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - transient_lastDdlTime 1366743639 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucketmapjoin_tmp_result - tmp directory: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10001 - - Stage: Stage-2 - Stats-Aggr Operator - Stats Aggregation Key Prefix: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10000/ - - Stage: Stage-3 - Map Reduce - Alias -> Map Operator Tree: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10002 - File Output Operator - compressed: false - GlobalTableId: 0 - directory: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10000 - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value1,value2 - columns.types string:string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result - name default.bucketmapjoin_tmp_result - serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - transient_lastDdlTime 1366743639 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucketmapjoin_tmp_result - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Needs Tagging: false - Path -> Alias: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10002 [hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10002] - Path -> Partition: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10002 - Partition - base file name: -ext-10002 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value1,value2 - columns.types string:string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result - name default.bucketmapjoin_tmp_result - serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - transient_lastDdlTime 1366743639 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value1,value2 - columns.types string:string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result - name default.bucketmapjoin_tmp_result - serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - transient_lastDdlTime 1366743639 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucketmapjoin_tmp_result - name: default.bucketmapjoin_tmp_result - Truncated Path -> Alias: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10002 [hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10002] - - Stage: Stage-5 - Map Reduce - Alias -> Map Operator Tree: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10002 - File Output Operator - compressed: false - GlobalTableId: 0 - directory: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10000 - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value1,value2 - columns.types string:string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result - name default.bucketmapjoin_tmp_result - serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - transient_lastDdlTime 1366743639 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucketmapjoin_tmp_result - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Needs Tagging: false - Path -> Alias: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10002 [hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10002] - Path -> Partition: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10002 - Partition - base file name: -ext-10002 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value1,value2 - columns.types string:string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result - name default.bucketmapjoin_tmp_result - serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - transient_lastDdlTime 1366743639 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value1,value2 - columns.types string:string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result - name default.bucketmapjoin_tmp_result - serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - transient_lastDdlTime 1366743639 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucketmapjoin_tmp_result - name: default.bucketmapjoin_tmp_result - Truncated Path -> Alias: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10002 [hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10002] - - Stage: Stage-6 - Move Operator - files: - hdfs directory: true - source: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10002 - destination: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-00-39_907_3836130325622754442/-ext-10000 - - - - -insert overwrite table bucketmapjoin_tmp_result -select /*+mapjoin(a)*/ a.key, a.value, b.value -from srcbucket_mapjoin a join srcbucket_mapjoin_part b -on a.key=b.key -Deleted /user/hive/warehouse/bucketmapjoin_tmp_result - - -select count(1) from bucketmapjoin_tmp_result -928 - -insert overwrite table bucketmapjoin_hash_result_1 -select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result -Deleted /user/hive/warehouse/bucketmapjoin_hash_result_1 -set hive.optimize.bucketmapjoin = false - -insert overwrite table bucketmapjoin_tmp_result -select /*+mapjoin(a)*/ a.key, a.value, b.value -from srcbucket_mapjoin a join srcbucket_mapjoin_part b -on a.key=b.key -Deleted /user/hive/warehouse/bucketmapjoin_tmp_result - - -select count(1) from bucketmapjoin_tmp_result -928 - -insert overwrite table bucketmapjoin_hash_result_2 -select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result -Deleted /user/hive/warehouse/bucketmapjoin_hash_result_2 - - -select a.key-b.key, a.value1-b.value1, a.value2-b.value2 -from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b -on a.key = b.key -0 0 0 -set hive.optimize.bucketmapjoin = true - -explain extended -insert overwrite table bucketmapjoin_tmp_result -select /*+mapjoin(a)*/ a.key, a.value, b.value -from srcbucket_mapjoin a join srcbucket_mapjoin_part_2 b -on a.key=b.key -ABSTRACT SYNTAX TREE: - (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin) a) (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin_part_2) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME bucketmapjoin_tmp_result))) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST a))) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value))))) - -STAGE DEPENDENCIES: - Stage-9 is a root stage - Stage-1 depends on stages: Stage-9 - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 - Stage-5 - Stage-6 depends on stages: Stage-5 - -STAGE PLANS: - Stage: Stage-9 - Map Reduce Local Work - Alias -> Map Local Tables: - a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - a - TableScan - alias: a - GatherStats: false - HashTable Sink Operator - condition expressions: - 0 {key} {value} - 1 {value} - handleSkewJoin: false - keys: - 0 [Column[key]] - 1 [Column[key]] - Position of Big Table: 1 - Bucket Mapjoin Context: - Alias Bucket Base File Name Mapping: - a {ds=2008-04-08/srcbucket22.txt=[srcbucket20.txt], ds=2008-04-08/srcbucket23.txt=[srcbucket21.txt], ds=2008-04-09/srcbucket22.txt=[srcbucket20.txt], ds=2008-04-09/srcbucket23.txt=[srcbucket21.txt]} - Alias Bucket File Name Mapping: - a {hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket22.txt=[hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket20.txt], hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket23.txt=[hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket21.txt], hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-09/srcbucket22.txt=[hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket20.txt], hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-09/srcbucket23.txt=[hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket21.txt]} - Alias Bucket Output File Name Mapping: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket22.txt 0 - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket23.txt 1 - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-09/srcbucket22.txt 0 - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-09/srcbucket23.txt 1 - - Stage: Stage-1 - Map Reduce - Alias -> Map Operator Tree: - b - TableScan - alias: b - GatherStats: false - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} {value} - 1 {value} - handleSkewJoin: false - keys: - 0 [Column[key]] - 1 [Column[key]] - outputColumnNames: _col0, _col1, _col5 - Position of Big Table: 1 - Select Operator - expressions: - expr: _col0 - type: int - expr: _col1 - type: string - expr: _col5 - type: string - outputColumnNames: _col0, _col1, _col5 - Select Operator - expressions: - expr: _col0 - type: int - expr: _col1 - type: string - expr: _col5 - type: string - outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - GlobalTableId: 1 - directory: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10002 - NumFilesPerFileSink: 1 - Stats Publishing Key Prefix: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10000/ - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value1,value2 - columns.types string:string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result - name default.bucketmapjoin_tmp_result - numFiles 1 - numPartitions 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 17966 - transient_lastDdlTime 1366743737 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucketmapjoin_tmp_result - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - Local Work: - Map Reduce Local Work - Needs Tagging: false - Path -> Alias: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08 [b] - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-09 [b] - Path -> Partition: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08 - Partition - base file name: ds=2008-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - properties: - bucket_count 2 - bucket_field_name key - columns key,value - columns.types int:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08 - name default.srcbucket_mapjoin_part_2 - numFiles 2 - numPartitions 2 - numRows 0 - partition_columns ds - rawDataSize 0 - serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 3062 - transient_lastDdlTime 1366743638 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count 2 - bucket_field_name key - columns key,value - columns.types int:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2 - name default.srcbucket_mapjoin_part_2 - numFiles 4 - numPartitions 2 - numRows 0 - partition_columns ds - rawDataSize 0 - serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 6124 - transient_lastDdlTime 1366743639 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcbucket_mapjoin_part_2 - name: default.srcbucket_mapjoin_part_2 - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-09 - Partition - base file name: ds=2008-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - properties: - bucket_count 2 - bucket_field_name key - columns key,value - columns.types int:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-09 - name default.srcbucket_mapjoin_part_2 - numFiles 2 - numPartitions 2 - numRows 0 - partition_columns ds - rawDataSize 0 - serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 3062 - transient_lastDdlTime 1366743639 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count 2 - bucket_field_name key - columns key,value - columns.types int:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2 - name default.srcbucket_mapjoin_part_2 - numFiles 4 - numPartitions 2 - numRows 0 - partition_columns ds - rawDataSize 0 - serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 6124 - transient_lastDdlTime 1366743639 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcbucket_mapjoin_part_2 - name: default.srcbucket_mapjoin_part_2 - Truncated Path -> Alias: - /srcbucket_mapjoin_part_2/ds=2008-04-08 [b] - /srcbucket_mapjoin_part_2/ds=2008-04-09 [b] - - Stage: Stage-7 - Conditional Operator - - Stage: Stage-4 - Move Operator - files: - hdfs directory: true - source: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10002 - destination: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10000 - - Stage: Stage-0 - Move Operator - tables: - replace: true - source: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10000 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value1,value2 - columns.types string:string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result - name default.bucketmapjoin_tmp_result - numFiles 1 - numPartitions 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 17966 - transient_lastDdlTime 1366743737 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucketmapjoin_tmp_result - tmp directory: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10001 - - Stage: Stage-2 - Stats-Aggr Operator - Stats Aggregation Key Prefix: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10000/ - - Stage: Stage-3 - Map Reduce - Alias -> Map Operator Tree: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10002 - File Output Operator - compressed: false - GlobalTableId: 0 - directory: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10000 - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value1,value2 - columns.types string:string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result - name default.bucketmapjoin_tmp_result - numFiles 1 - numPartitions 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 17966 - transient_lastDdlTime 1366743737 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucketmapjoin_tmp_result - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Needs Tagging: false - Path -> Alias: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10002 [hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10002] - Path -> Partition: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10002 - Partition - base file name: -ext-10002 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value1,value2 - columns.types string:string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result - name default.bucketmapjoin_tmp_result - numFiles 1 - numPartitions 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 17966 - transient_lastDdlTime 1366743737 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value1,value2 - columns.types string:string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result - name default.bucketmapjoin_tmp_result - numFiles 1 - numPartitions 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 17966 - transient_lastDdlTime 1366743737 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucketmapjoin_tmp_result - name: default.bucketmapjoin_tmp_result - Truncated Path -> Alias: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10002 [hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10002] - - Stage: Stage-5 - Map Reduce - Alias -> Map Operator Tree: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10002 - File Output Operator - compressed: false - GlobalTableId: 0 - directory: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10000 - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value1,value2 - columns.types string:string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result - name default.bucketmapjoin_tmp_result - numFiles 1 - numPartitions 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 17966 - transient_lastDdlTime 1366743737 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucketmapjoin_tmp_result - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Needs Tagging: false - Path -> Alias: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10002 [hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10002] - Path -> Partition: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10002 - Partition - base file name: -ext-10002 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value1,value2 - columns.types string:string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result - name default.bucketmapjoin_tmp_result - numFiles 1 - numPartitions 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 17966 - transient_lastDdlTime 1366743737 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value1,value2 - columns.types string:string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result - name default.bucketmapjoin_tmp_result - numFiles 1 - numPartitions 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 17966 - transient_lastDdlTime 1366743737 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucketmapjoin_tmp_result - name: default.bucketmapjoin_tmp_result - Truncated Path -> Alias: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10002 [hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10002] - - Stage: Stage-6 - Move Operator - files: - hdfs directory: true - source: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10002 - destination: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_12-03-31_286_2769775196968737402/-ext-10000 - - - - -insert overwrite table bucketmapjoin_tmp_result -select /*+mapjoin(a)*/ a.key, a.value, b.value -from srcbucket_mapjoin a join srcbucket_mapjoin_part_2 b -on a.key=b.key -Deleted /user/hive/warehouse/bucketmapjoin_tmp_result - - -select count(1) from bucketmapjoin_tmp_result -0 - -insert overwrite table bucketmapjoin_hash_result_1 -select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result -Deleted /user/hive/warehouse/bucketmapjoin_hash_result_1 -set hive.optimize.bucketmapjoin = false - -insert overwrite table bucketmapjoin_tmp_result -select /*+mapjoin(a)*/ a.key, a.value, b.value -from srcbucket_mapjoin a join srcbucket_mapjoin_part_2 b -on a.key=b.key -Deleted /user/hive/warehouse/bucketmapjoin_tmp_result - - -select count(1) from bucketmapjoin_tmp_result -0 - -insert overwrite table bucketmapjoin_hash_result_2 -select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result -Deleted /user/hive/warehouse/bucketmapjoin_hash_result_2 - - -select a.key-b.key, a.value1-b.value1, a.value2-b.value2 -from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b -on a.key = b.key -NULL NULL NULL
http://git-wip-us.apache.org/repos/asf/bigtop/blob/e209fdbb/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/drop_multi_partitions/in ---------------------------------------------------------------------- diff --git a/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/drop_multi_partitions/in b/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/drop_multi_partitions/in deleted file mode 100644 index e1a0dbf..0000000 --- a/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/drop_multi_partitions/in +++ /dev/null @@ -1,31 +0,0 @@ --- Licensed to the Apache Software Foundation (ASF) under one or more --- contributor license agreements. See the NOTICE file distributed with --- this work for additional information regarding copyright ownership. --- The ASF licenses this file to You under the Apache License, Version 2.0 --- (the "License") you may not use this file except in compliance with --- the License. You may obtain a copy of the License at --- --- http://www.apache.org/licenses/LICENSE-2.0 --- --- Unless required by applicable law or agreed to in writing, software --- distributed under the License is distributed on an "AS IS" BASIS, --- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. --- See the License for the specific language governing permissions and --- limitations under the License. -create table mp (a string) partitioned by (b string, c string); - -alter table mp add partition (b='1', c='1'); -alter table mp add partition (b='1', c='2'); -alter table mp add partition (b='2', c='2'); - -show partitions mp; - -explain extended alter table mp drop partition (b='1'); -alter table mp drop partition (b='1'); - -show partitions mp; - -set hive.exec.drop.ignorenonexistent=false; -alter table mp drop if exists partition (b='3'); - -show partitions mp; http://git-wip-us.apache.org/repos/asf/bigtop/blob/e209fdbb/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/drop_multi_partitions/out ---------------------------------------------------------------------- diff --git a/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/drop_multi_partitions/out b/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/drop_multi_partitions/out deleted file mode 100644 index edc8e7c..0000000 --- a/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/drop_multi_partitions/out +++ /dev/null @@ -1,43 +0,0 @@ -create table mp (a string) partitioned by (b string, c string) - - -alter table mp add partition (b='1', c='1') - -alter table mp add partition (b='1', c='2') - -alter table mp add partition (b='2', c='2') - - -show partitions mp -b=1/c=1 -b=1/c=2 -b=2/c=2 - - -explain extended alter table mp drop partition (b='1') -ABSTRACT SYNTAX TREE: - (TOK_ALTERTABLE_DROPPARTS mp (TOK_PARTSPEC (TOK_PARTVAL b = '1'))) - -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Drop Table Operator: - Drop Table - table: mp - - - -alter table mp drop partition (b='1') - - -show partitions mp -b=2/c=2 -set hive.exec.drop.ignorenonexistent=false - -alter table mp drop if exists partition (b='3') - - -show partitions mp -b=2/c=2 http://git-wip-us.apache.org/repos/asf/bigtop/blob/e209fdbb/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/groupby_map_ppr_multi_distinct/filter ---------------------------------------------------------------------- diff --git a/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/groupby_map_ppr_multi_distinct/filter b/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/groupby_map_ppr_multi_distinct/filter deleted file mode 100644 index ff8759e..0000000 --- a/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/groupby_map_ppr_multi_distinct/filter +++ /dev/null @@ -1,5 +0,0 @@ -sed -re 's#hdfs://[^/]*/#hdfs://HADOOP/#' \ - -e 's#hdfs://.*/-(ext|mr)-1000#hdfs://HADOOP/-\1-1000#' \ - -e 's#transient_lastDdlTime [0-9]*#transient_lastDdlTime JUSTNOW#' \ - -e 's#file:/.*/-(ext|mr)-1000#file:/HADOOP/-\1-1000#' \ - -e '/.*jobconf.xml:an attempt to override final parameter: mapreduce.job.end-notification.*; Ignoring\./ d' http://git-wip-us.apache.org/repos/asf/bigtop/blob/e209fdbb/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/groupby_map_ppr_multi_distinct/in ---------------------------------------------------------------------- diff --git a/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/groupby_map_ppr_multi_distinct/in b/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/groupby_map_ppr_multi_distinct/in deleted file mode 100644 index 7e806d3..0000000 --- a/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/groupby_map_ppr_multi_distinct/in +++ /dev/null @@ -1,34 +0,0 @@ --- Licensed to the Apache Software Foundation (ASF) under one or more --- contributor license agreements. See the NOTICE file distributed with --- this work for additional information regarding copyright ownership. --- The ASF licenses this file to You under the Apache License, Version 2.0 --- (the "License") you may not use this file except in compliance with --- the License. You may obtain a copy of the License at --- --- http://www.apache.org/licenses/LICENSE-2.0 --- --- Unless required by applicable law or agreed to in writing, software --- distributed under the License is distributed on an "AS IS" BASIS, --- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. --- See the License for the specific language governing permissions and --- limitations under the License. -set hive.map.aggr=true; -set hive.groupby.skewindata=false; -set mapred.reduce.tasks=31; - -CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, C3 INT, c4 INT) STORED AS TEXTFILE; - -EXPLAIN EXTENDED -FROM srcpart src -INSERT OVERWRITE TABLE dest1 -SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value) -WHERE src.ds = '2008-04-08' -GROUP BY substr(src.key,1,1); - -FROM srcpart src -INSERT OVERWRITE TABLE dest1 -SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value) -WHERE src.ds = '2008-04-08' -GROUP BY substr(src.key,1,1); - -SELECT dest1.* FROM dest1; http://git-wip-us.apache.org/repos/asf/bigtop/blob/e209fdbb/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/groupby_map_ppr_multi_distinct/out ---------------------------------------------------------------------- diff --git a/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/groupby_map_ppr_multi_distinct/out b/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/groupby_map_ppr_multi_distinct/out deleted file mode 100644 index a4dac68..0000000 --- a/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/groupby_map_ppr_multi_distinct/out +++ /dev/null @@ -1,301 +0,0 @@ -set hive.map.aggr=true -set hive.groupby.skewindata=false -set mapred.reduce.tasks=31 - - -CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, C3 INT, c4 INT) STORED AS TEXTFILE - - -EXPLAIN EXTENDED -FROM srcpart src -INSERT OVERWRITE TABLE dest1 -SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value) -WHERE src.ds = '2008-04-08' -GROUP BY substr(src.key,1,1) -ABSTRACT SYNTAX TREE: - (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME srcpart) src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest1))) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1)) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION concat (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1) (TOK_FUNCTION sum (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5)))) (TOK_SELEXPR (TOK_FUNCTIONDI sum (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTIONDI count (. (TOK_TABLE_OR_COL src) value)))) (TOK_WHERE (= (. (TOK_TABLE_OR_COL src) ds) '2008-04-08')) (TOK_GROUPBY (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1)))) - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Alias -> Map Operator Tree: - src - TableScan - alias: src - GatherStats: false - Select Operator - expressions: - expr: key - type: string - expr: value - type: string - outputColumnNames: key, value - Group By Operator - aggregations: - expr: count(DISTINCT substr(value, 5)) - expr: sum(substr(value, 5)) - expr: sum(DISTINCT substr(value, 5)) - expr: count(DISTINCT value) - bucketGroup: false - keys: - expr: substr(key, 1, 1) - type: string - expr: substr(value, 5) - type: string - expr: value - type: string - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Reduce Output Operator - key expressions: - expr: _col0 - type: string - expr: _col1 - type: string - expr: _col2 - type: string - sort order: +++ - Map-reduce partition columns: - expr: _col0 - type: string - tag: -1 - value expressions: - expr: _col3 - type: bigint - expr: _col4 - type: double - expr: _col5 - type: double - expr: _col6 - type: bigint - Needs Tagging: false - Path -> Alias: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcpart/ds=2008-04-08/hr=11 [src] - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcpart/ds=2008-04-08/hr=12 [src] - Path -> Partition: - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcpart/ds=2008-04-08/hr=11 - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - bucket_count -1 - columns key,value - columns.types string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcpart/ds=2008-04-08/hr=11 - name default.srcpart - numFiles 1 - numPartitions 4 - numRows 0 - partition_columns ds/hr - rawDataSize 0 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 - transient_lastDdlTime 1366737715 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.types string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcpart - name default.srcpart - numFiles 4 - numPartitions 4 - numRows 0 - partition_columns ds/hr - rawDataSize 0 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 23248 - transient_lastDdlTime 1366737718 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcpart/ds=2008-04-08/hr=12 - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - bucket_count -1 - columns key,value - columns.types string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcpart/ds=2008-04-08/hr=12 - name default.srcpart - numFiles 1 - numPartitions 4 - numRows 0 - partition_columns ds/hr - rawDataSize 0 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 - transient_lastDdlTime 1366737716 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.types string:string - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/srcpart - name default.srcpart - numFiles 4 - numPartitions 4 - numRows 0 - partition_columns ds/hr - rawDataSize 0 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 23248 - transient_lastDdlTime 1366737718 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Reduce Operator Tree: - Group By Operator - aggregations: - expr: count(DISTINCT KEY._col1:0._col0) - expr: sum(VALUE._col1) - expr: sum(DISTINCT KEY._col1:1._col0) - expr: count(DISTINCT KEY._col1:2._col0) - bucketGroup: false - keys: - expr: KEY._col0 - type: string - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Select Operator - expressions: - expr: _col0 - type: string - expr: _col1 - type: bigint - expr: concat(_col0, _col2) - type: string - expr: _col3 - type: double - expr: _col4 - type: bigint - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Select Operator - expressions: - expr: _col0 - type: string - expr: UDFToInteger(_col1) - type: int - expr: _col2 - type: string - expr: UDFToInteger(_col3) - type: int - expr: UDFToInteger(_col4) - type: int - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - File Output Operator - compressed: false - GlobalTableId: 1 - directory: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_11-34-17_553_86036101665952261/-ext-10000 - NumFilesPerFileSink: 1 - Stats Publishing Key Prefix: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_11-34-17_553_86036101665952261/-ext-10000/ - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,c1,c2,c3,c4 - columns.types string:int:string:int:int - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/dest1 - name default.dest1 - serialization.ddl struct dest1 { string key, i32 c1, string c2, i32 c3, i32 c4} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - transient_lastDdlTime 1366742057 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [src] - /srcpart/ds=2008-04-08/hr=12 [src] - - Stage: Stage-0 - Move Operator - tables: - replace: true - source: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_11-34-17_553_86036101665952261/-ext-10000 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,c1,c2,c3,c4 - columns.types string:int:string:int:int - file.inputformat org.apache.hadoop.mapred.TextInputFormat - file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/user/hive/warehouse/dest1 - name default.dest1 - serialization.ddl struct dest1 { string key, i32 c1, string c2, i32 c3, i32 c4} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - transient_lastDdlTime 1366742057 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 - tmp directory: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_11-34-17_553_86036101665952261/-ext-10001 - - Stage: Stage-2 - Stats-Aggr Operator - Stats Aggregation Key Prefix: hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_11-34-17_553_86036101665952261/-ext-10000/ - - - - -FROM srcpart src -INSERT OVERWRITE TABLE dest1 -SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value) -WHERE src.ds = '2008-04-08' -GROUP BY substr(src.key,1,1) -Deleted /user/hive/warehouse/dest1 - - -SELECT dest1.* FROM dest1 -0 1 00.0 0 1 -1 71 132828.0 10044 71 -2 69 251142.0 15780 69 -3 62 364008.0 20119 62 -4 74 4105526.0 30965 74 -5 6 5794.0 278 6 -6 5 6796.0 331 5 -7 6 71470.0 447 6 -8 8 81524.0 595 8 -9 7 92094.0 577 7 http://git-wip-us.apache.org/repos/asf/bigtop/blob/e209fdbb/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/index_creation/filter ---------------------------------------------------------------------- diff --git a/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/index_creation/filter b/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/index_creation/filter deleted file mode 100644 index 2aa66f0..0000000 --- a/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/index_creation/filter +++ /dev/null @@ -1,8 +0,0 @@ -sed -re 's#hdfs://.*/-(ext|mr)-1000#hdfs://HADOOP/-\1-1000#' | -sed -e 's#hdfs://[^/]*/#hdfs://HADOOP/#' \ - -e 's#owner:[^,]*,#owner:BORG,#' \ - -e 's#createTime:[0-9]*,#createTime:JUSTNOW#' \ - -e 's#location:hdfs://[^/]*/#location:hdfs://HADOOP/#' \ - -e 's#transient_lastDdlTime=[0-9]*}#transient_lastDdlTime=JUSTNOW}#' \ - -e '/.*jobconf.xml:an attempt to override final parameter: mapreduce.job.end-notification.*; Ignoring\./ d' - http://git-wip-us.apache.org/repos/asf/bigtop/blob/e209fdbb/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/index_creation/in ---------------------------------------------------------------------- diff --git a/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/index_creation/in b/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/index_creation/in deleted file mode 100644 index 91107ae..0000000 --- a/bigtop-tests/test-artifacts/hive/src/main/resources/scripts/ql/index_creation/in +++ /dev/null @@ -1,66 +0,0 @@ --- Licensed to the Apache Software Foundation (ASF) under one or more --- contributor license agreements. See the NOTICE file distributed with --- this work for additional information regarding copyright ownership. --- The ASF licenses this file to You under the Apache License, Version 2.0 --- (the "License") you may not use this file except in compliance with --- the License. You may obtain a copy of the License at --- --- http://www.apache.org/licenses/LICENSE-2.0 --- --- Unless required by applicable law or agreed to in writing, software --- distributed under the License is distributed on an "AS IS" BASIS, --- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. --- See the License for the specific language governing permissions and --- limitations under the License. -drop index src_index_2 on src; -drop index src_index_3 on src; -drop index src_index_4 on src; -drop index src_index_5 on src; -drop index src_index_6 on src; -drop index src_index_7 on src; -drop index src_index_8 on src; -drop index src_index_9 on src; -drop table `_t`; - -create index src_index_2 on table src(key) as 'compact' WITH DEFERRED REBUILD; -desc extended default__src_src_index_2__; - -create index src_index_3 on table src(key) as 'compact' WITH DEFERRED REBUILD in table src_idx_src_index_3; -desc extended src_idx_src_index_3; - -create index src_index_4 on table src(key) as 'compact' WITH DEFERRED REBUILD ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' STORED AS TEXTFILE; -desc extended default__src_src_index_4__; - -create index src_index_5 on table src(key) as 'compact' WITH DEFERRED REBUILD ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' ESCAPED BY '\\'; -desc extended default__src_src_index_5__; - -create index src_index_6 on table src(key) as 'compact' WITH DEFERRED REBUILD STORED AS RCFILE; -desc extended default__src_src_index_6__; - -create index src_index_7 on table src(key) as 'compact' WITH DEFERRED REBUILD in table src_idx_src_index_7 STORED AS RCFILE; -desc extended src_idx_src_index_7; - -create index src_index_8 on table src(key) as 'compact' WITH DEFERRED REBUILD IDXPROPERTIES ("prop1"="val1", "prop2"="val2"); -desc extended default__src_src_index_8__; - -create index src_index_9 on table src(key) as 'compact' WITH DEFERRED REBUILD TBLPROPERTIES ("prop1"="val1", "prop2"="val2"); -desc extended default__src_src_index_9__; - -create table `_t`(`_i` int, `_j` int); -create index x on table `_t`(`_j`) as 'compact' WITH DEFERRED REBUILD; -alter index x on `_t` rebuild; - -create index x2 on table `_t`(`_i`,`_j`) as 'compact' WITH DEFERRED -REBUILD; -alter index x2 on `_t` rebuild; - -drop index src_index_2 on src; -drop index src_index_3 on src; -drop index src_index_4 on src; -drop index src_index_5 on src; -drop index src_index_6 on src; -drop index src_index_7 on src; -drop index src_index_8 on src; -drop index src_index_9 on src; -drop table `_t`; -
